vacuum_embeddings

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description clearly states the tool is safe and idempotent, and specifies what it does (drops orphaned rows) and what it does not affect (live data). With no annotations provided, the description carries the burden well, though it omits details about return values or edge cases.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise with two sentences: the first states the core purpose, the second adds safety and context. Every sentence adds value and is front-loaded with the key action.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (one parameter, no output schema), the description fully covers what an agent needs: purpose, safety, and typical usage scenario. It is complete for the task at hand.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has one required parameter 'vault' with 0% description coverage. The tool description does not explain what 'vault' represents or how to use it, leaving the agent without guidance on this crucial parameter.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Drop orphaned embedding rows') and the specific condition ('whose chunk_id no longer exists in the chunks table'). It distinguishes this tool from siblings by mentioning safety and idempotence, and the context of post-migration cleanup.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly mentions the use case ('after migrations from pre-v0.7.0 schemas') and assures safety ('does not touch live data'). While it does not name alternative tools, the context makes it clear this is for maintenance, not regular operations.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.